LMArena · GPQA · SWE-bench · HLE · ARC-AGI · OSWorld · BFCL
AI 模型評測
1079 個模型在 23 項公開基準上的 3086 筆成績，每個數字都連到原始出處，廠商自報另行標註。
3086 筆成績 1079 個模型 23 項基準 更新於 2026年10月22日
Current champions
The top model on each core benchmark. Only official leaderboards, independent evaluations and compiled data count; vendor self-reports are excluded.
LMArena Text Gemini 4 Argon 1525 人類偏好 GPQA Diamond Gemini 4 Argon 96.4% 科學 Humanity's Last Exam GPT-6 Astra 54.8% 知識 AIME (OTIS Mock AIME 2024–2025) Gemini 4 Argon 100.0% 數學 SWE-bench Verified Claude Opus 4.7 83.5% Agent 程式設計 Terminal-Bench 2.0 GPT-5.5 84.7% Agent 程式設計 OSWorld (Verified) Claude Sonnet 4.6 72.1% 電腦操作 τ²-bench Gemini 3.0 Pro 85.3% 工具呼叫與 Agent BFCL v4 (function calling) Claude Opus 4.5 77.5% 工具呼叫與 Agent MMLU-Pro Gemini 3.1 Pro 91.2% 知識
模型 × 基準矩陣
每格為該模型在該基準主設定下的最佳成績，優先採用官方榜單與獨立評測；◇ 表示僅有廠商自報或論文數據。點擊欄名排序，勾選模型可比較。
| 模型 | LMArena Text | GPQA Diamond | Humanity's Last Exam | AIME (OTIS Mock AIME 2024–2025) | SWE-bench Verified | Terminal-Bench 2.0 | OSWorld (Verified) | τ²-bench | BFCL v4 (function calling) | MMLU-Pro |
|---|---|---|---|---|---|---|---|---|---|---|
| GPT-5.2OpenAI | 1437 | 91.4% | 27.8% | 96.1% | 73.8% | 64.9% | — | 81.6% | 55.9% | 87.4% ◇ |
| Gemini 3 ProGoogle | 1486 | 92.6% | 37.5% | 91.4% | 77.4% | 69.4% | — | 75.9% | 72.5% | 90.1% ◇ |
| Claude Sonnet 4.5Anthropic | 1456 | 82.3% | 13.7% | 77.8% | 74.8% | 46.5% | 62.9% | 72.4% | 73.2% | — |
| GPT-5OpenAI | 1435 | 86.2% | 25.3% | 91.4% | 74.4% | 49.6% | — | 81.6% | — | 87.1% ◇ |
| o3OpenAI | 1432 | 81.8% | 20.3% | 84.4% | 62.3% | — | 23.0% | 73.9% ◇ | 63.0% | — |
| Claude Opus 4.5Anthropic | 1474 | 86.0% | 25.2% | 86.1% | 79.2% | 63.1% | 66.3% ◇ | 79.6% | 77.5% | — |
| Gemini 2.5 Pro (Jun 2025)Google | 1446 | 85.3% | 21.6% | 84.7% | 57.6% | 32.6% | — | — | — | 86.0% ◇ |
| Claude Sonnet 4Anthropic | 1402 | 79.2% | 7.8% | 68.9% | 76.8% | — | 43.9% | 80.5% ◇ | — | — |
| o4-miniOpenAI | 1391 | 79.6% | 18.1% | 81.7% | 64.6% | — | — | 68.3% | 53.2% | — |
| GPT-4.1OpenAI | 1415 | 66.9% | 5.4% | 38.3% | 48.5% | — | — | 74.0% | 54.0% | 81.8% ◇ |
| Claude 3.7 SonnetAnthropic | 1388 | 79.7% | 8.0% | 57.8% | 66.4% | — | 35.8% | 72.1% | — | 84.0% ◇ |
| Qwen2.5-72BAlibaba (Qwen) | 1303 | 49.1% | — | 8.1% | — | — | 5.0% | — | — | 71.6% ◇ |
| Claude Opus 4.7Anthropic | 1501 | 90.2% | 36.2% | 97.8% | 83.5% | 80.2% | — | — | — | — |
| GPT-5.4OpenAI | 1475 | 93.3% | 36.2% | 97.8% | 76.9% | 81.8% | — | — | — | 87.5% ◇ |
| Gemini 3.1 ProGoogle | 1487 | 94.4% | 46.4% | 95.6% | 75.6% | 80.2% | — | — | — | 91.2% |
| Claude Sonnet 4.6Anthropic | 1472 | 87.4% | — | 85.8% | 75.2% | 53.4% | 72.1% | — | — | — |
| Kimi K2.5Moonshot AI | 1450 | 87.6% | 24.4% | 92.2% | 73.8% | 43.2% | 63.3% | — | — | — |
| GPT-5.1OpenAI | 1456 | 87.6% | 23.7% | 88.6% | 68.0% | 47.6% | — | — | — | 86.4% ◇ |
| GPT-5 miniOpenAI | 1390 | 75.0% | 19.4% | 86.7% | 64.7% | 34.8% | — | — | 55.5% | — |
| Claude Opus 4Anthropic | 1426 | 76.3% | 10.7% | 64.4% | 70.7% | — | — | 81.4% ◇ | — | — |
| Gemini 1.5 Pro (Sept 2024)Google | 1351 | 57.2% | 4.6% | 23.1% | — | — | — | — | — | 70.3% |
| Claude 3.5 SonnetAnthropic | 1374 | 54.0% | — | 6.5% | 63.4% | — | — | — | — | 77.6% |
| GPT-4o (May 2024)OpenAI | 1346 | 48.9% | — | 6.3% | 38.8% | — | — | — | — | 72.5% |
| Claude 3 HaikuAnthropic | 1262 | 36.3% | — | 1.8% | 40.6% | — | — | — | — | 42.3% |
| GPT-4 Turbo (Nov 2023)OpenAI | 1325 | 42.4% | — | — | 22.4% | — | — | — | — | 63.7% |
| GLM-5Zhipu AI (Z.ai) | 1458 | 87.8% | — | 80.0% | 72.8% | 52.4% | — | 73.7% | — | 86.0% ◇ |
| Claude Opus 4.6Anthropic | 1504 | 90.5% | 34.4% | 94.4% | 78.7% | 79.8% | — | — | — | — |
| Gemini 3 FlashGoogle | 1473 | 89.4% | — | 95.6% | 75.8% | 64.3% | — | 76.8% | — | — |
| DeepSeek-V3.2DeepSeek | 1425 | 83.4% | — | 87.8% | 70.0% | 39.5% | — | 81.1% ◇ | — | 85.0% ◇ |
| Claude Haiku 4.5Anthropic | 1414 | 71.2% | — | 66.7% | 66.6% | 35.5% | — | — | 68.7% | — |
| GPT-5 nanoOpenAI | 1337 | 69.4% | — | 81.1% | 34.8% | 21.8% | — | — | 51.5% | — |
| Claude Opus 4.1Anthropic | 1450 | 76.8% | 11.5% | 68.9% | 73.3% | 38.0% | — | 82.4% ◇ | — | — |
| GPT-4.1 miniOpenAI | 1383 | 65.8% | — | 44.7% | 23.9% | — | — | 61.4% | 50.5% | — |
| Phi-4Microsoft Research | 1256 | 56.1% | — | 13.8% | — | — | — | — | 28.8% | 70.4% ◇ |
| Llama 3.3 70BMeta | 1318 | 47.4% | — | 5.1% | — | — | — | — | 31.9% | 65.9% |
| Gemini 1.5 Flash (Sep 2024)Google | 1309 | 47.3% | — | 16.3% | — | — | — | — | — | 64.1% |
| Llama 3.1-8BMeta | 1211 | 27.0% | — | 1.7% | — | — | — | — | 25.8% | 36.6% |
| GPT-4o miniOpenAI | 1318 | 37.7% | — | 6.9% | — | — | — | — | — | 63.1% |
| Claude 3 OpusAnthropic | 1322 | 47.2% | — | 4.7% | 15.8% | — | — | — | — | 68.5% |
| Gemini 3.8 FlashGoogle | 1497 | 95.4% | 44.5% | 98.9% | — | — | — | — | — | — |
全部基準
程式設計
LMArena WebDev持續更新 Arena where two models each build a web app from the same prompt and users vote on the result. 127 個模型 · 最高: 1813 LiveCodeBench近期未更新 Coding problems collected continuously from LeetCode, AtCoder and Codeforces with their release dates, so models can be scored only on problems published after their training cut-off. 22 個模型 · 最高: 75.8% HumanEval / HumanEval+已飽和 164 hand-written Python function problems from OpenAI (2021). EvalPlus adds many more tests per problem (HumanEval+) to catch wrong solutions that pass the original tests. 122 個模型 · 最高: 89.0%
綜合
Open LLM Leaderboard v2已封存 Hugging Face's leaderboard of open-weight models, scored on IFEval, BBH, MATH Lvl 5, GPQA, MuSR and MMLU-Pro with normalised scores. The leaderboard was archived in 2025 and no longer accepts submissions. 294 個模型 · 最高: 48.0% Artificial Analysis Intelligence Index僅連結 Independent composite index that runs a battery of evaluations plus price and speed measurements across API models. 僅連結
知識
MMLU已飽和 About 14,000 multiple-choice questions over 57 subjects, from elementary maths to law and medicine. 158 個模型 · 最高: 88.1% MMLU-Pro持續更新 Harder successor to MMLU: about 12,000 reasoning-heavy questions in 14 disciplines with 10 answer options. 243 個模型 · 最高: 91.2% Humanity's Last Exam持續更新 About 2,500 expert-written questions across 100+ subjects from the Center for AI Safety and Scale AI, filtered to stump frontier models at creation time. 46 個模型 · 最高: 54.8%
Agent 程式設計
SWE-bench Verified有爭議 500 human-validated GitHub issues from 12 Python repositories; the system must produce a patch that makes the hidden tests pass. 81 個模型 · 最高: 83.5% SWE-bench Pro僅連結 Scale AI's harder, longer-horizon successor to SWE-bench with a 731-task public split and private/commercial splits. 僅連結 Terminal-Bench 2.0持續更新 Hard, realistic tasks an agent must finish in a sandboxed terminal (Stanford × Laude Institute). 45 個模型 · 最高: 84.7%
數學
AIME (OTIS Mock AIME 2024–2025)持續更新 AIME-style competition maths (integer answers 0–999). We use Epoch AI's runs on the OTIS Mock AIME 2024–2025 papers, which are less exposed than past official AIME papers. 200 個模型 · 最高: 100.0% MATH Level 5已飽和 The hardest (level 5) problems of the MATH competition dataset (Hendrycks et al., 2021). 94 個模型 · 最高: 98.1%
抽象推理
ARC-AGI-1已飽和 Abstract grid puzzles (François Chollet) that test learning a new rule from a few examples. 6 個模型 · 最高: 98.5% ARC-AGI-2持續更新 Harder second version of ARC-AGI (2025), designed so that brute-force search is not enough. 4 個模型 · 最高: 95.0% ARC-AGI-3持續更新 Interactive, game-like third version of ARC-AGI that tests exploration and learning inside novel environments. 3 個模型 · 最高: 99.9%
電腦操作
工具呼叫與 Agent
τ²-bench持續更新 Sierra's customer-service agent benchmark: the agent follows a policy and uses tools while an LLM-simulated user talks to it (retail, airline, telecom, banking). 43 個模型 · 最高: 85.3% BFCL v4 (function calling)持續更新 Berkeley Function Calling Leaderboard: single, parallel and multi-turn tool calls, web search, memory and relevance detection. 80 個模型 · 最高: 77.5%
中文
CMMLU近期未更新 Chinese multitask knowledge benchmark: 67 subjects including China-specific topics. 12 個模型 · 最高: 90.3% C-Eval近期未更新 Chinese evaluation suite of about 13,900 multiple-choice questions over 52 disciplines and four difficulty levels. 11 個模型 · 最高: 68.7% SuperCLUE僅連結 Periodic Chinese general-capability evaluation of domestic and international models, published as reports. 僅連結
採集方法
- We read official data files and public datasets (Hugging Face, GitHub, CSV downloads) and never invent or estimate scores.
- Model names from different leaderboards are merged into one model page (for example dated versions and reasoning-effort variants).
- Leaderboards that restrict reuse are cited with their top entries only, or linked without copying.
- Data is refreshed by a repeatable script; each run keeps a dated snapshot so changes can be compared over time.
來源類型
- 官方榜單
- The benchmark maintainers' own leaderboard
- 獨立評測
- An independent evaluator ran the model itself (e.g. Epoch AI)
- 廠商自報
- Self-reported or submitted by the model developer
- 論文 / 技術報告
- Reported in a paper or technical report (usually by the developer)
- 第三方彙編
- Compiled by Epoch AI; the original source is not given per row
資料來源與授權
| 來源 | 授權 / 條款 | 本站使用方式 | 最近抓取 |
|---|---|---|---|
| LMArena leaderboard dataset LMArena, Arena Leaderboard Dataset (Hugging Face), CC BY 4.0 | CC BY 4.0 | Open licence – full data with attribution | 2026年10月10日 ⚠︎ |
| Epoch AI Benchmarking Hub Epoch AI, 'Capabilities & benchmarking', https://epoch.ai/benchmarks (CC BY 4.0) | CC BY 4.0 | Open licence – full data with attribution | 2026年10月22日 |
| SWE-bench leaderboards (swebench.com) SWE-bench team, swebench.com leaderboards | No explicit licence (NOASSERTION) – factual scores only, with citation | No explicit licence – factual scores only, with citation | 2026年10月22日 |
| LiveCodeBench leaderboard LiveCodeBench (Jain et al.), livecodebench.github.io | No explicit licence on the site repo (benchmark code MIT) – factual scores only, with citation | No explicit licence – factual scores only, with citation | 2026年10月22日 |
| EvalPlus leaderboard EvalPlus team, evalplus.github.io | Apache-2.0 (site repo) | Open licence – full data with attribution | 2026年10月22日 |
| Berkeley Function Calling Leaderboard (BFCL) Gorilla / BFCL team, UC Berkeley | Apache-2.0 (gorilla repo) | Open licence – full data with attribution | 2026年10月22日 |
| τ²-bench leaderboard submissions Sierra Research, τ²-bench | MIT (repo) | Open licence – full data with attribution | 2026年10月22日 |
| MMLU-Pro leaderboard (TIGER-Lab) TIGER-Lab, MMLU-Pro leaderboard | Apache-2.0 (dataset) | Open licence – full data with attribution | 2026年10月22日 |
| Hugging Face Open LLM Leaderboard v2 (archived) Hugging Face, Open LLM Leaderboard (archived 2025) | No licence tag – factual scores only, with citation | No explicit licence – factual scores only, with citation 4576 rows in archive; 353 official-developer models kept | 2026年10月22日 |
| ARC Prize leaderboard ARC Prize Foundation, arcprize.org/leaderboard | ARC Prize Terms: no copying/aggregation for commercial purposes without permission | Restricted – only top entries cited top 10 per set only (terms) | 2026年10月22日 |
| CMMLU leaderboard (GitHub README) Li et al., CMMLU (CC BY-NC-SA 4.0) | CC BY-NC-SA 4.0 | Restricted – only top entries cited | 2026年10月22日 |
| C-Eval (GitHub README, initial release table) Huang et al., C-Eval | Code MIT; dataset CC BY-NC-SA 4.0 | Restricted – only top entries cited | 2026年10月22日 |
| Artificial Analysis Artificial Analysis | Free API requires an API key and attribution; no open bulk data | Not collected – link only | — |
| SuperCLUE CLUE / SuperCLUE | No open data interface | Not collected – link only | — |
| Scale AI SEAL leaderboards (SWE-bench Pro, HLE) Scale AI | No open data interface | Not collected – link only | — |
給 AI agent 用
The same data as JSON: benchmark metadata with licences, every model's best scores and per-benchmark result lists with source links.
/api/benchmarks.json/api/benchmarks/matrix.json/api/benchmarks/<id>.json/llms.txt